期刊文献+

基于图像纹理特征和多级SVM的浮选过程状态识别方法 被引量:7

Research on recognizing flotation states based on image texture features and multi-layer SVMs
原文传递
导出
摘要 针对浮选泡沫图像的纹理特征,采用多级支持向量机(MLSVMs)方法对浮选生产过程状态进行识别.首先基于灰度共生矩阵,提取浮选泡沫图像的诸如能量、熵及惯性等纹理特性参数来描述浮选泡沫的视觉特征;然后采用归一化后的纹理特征数据样本分别对多级支持向量机进行训练和识别.MLSVMs模型核函数参数采用改进惯性权重的粒子群算法进行优化.测试结果表明,所提出的方法在训练时间和识别正确率上具有较好的性能,可以满足浮选过程的实时监控要求. According to the characteristics of the flotation froth image texture features,a method for the extraction of significant patterns based on multi-layer SVMs(MLSVMs) is introduced.Firstly,the numerical flotation froth image is analyzed to extract texture features,such as energy,entropy and inertia,based on grey-level co-occurrence matrix(GLCM) to provide qualitative information on the changes in the visual appearance of the froth.MLSVMs classifier,which is trained with the sampling data from above texture features,identifies out the three types of flotation production states.The particle swarm optimization(PSO) algorithm with improved inertia weights is adopted to optimize kernal function parameters of MLSVMs.The test results show that the proposed classifier has an excellent performance on training speed and correct recognization ratio,and meets the requirement for real-time monitor for the flotation process.
出处 《控制与决策》 EI CSCD 北大核心 2010年第10期1523-1526,1535,共5页 Control and Decision
基金 辽宁省教育厅高等学校科研基金项目(20060432) 辽宁省教育厅创新团队基金项目(2008T091)
关键词 浮选过程 纹理特征 多级支持向量机 粒子群算法 Flotation process Texture features Multi-layer SVM Particle swarm optimization
作者简介 王介生(1977-),男,山西介休人,副教授,博士,从事复杂工业过程建模的研究; 高宪文(1954-),男,辽宁盘锦人,教授,博士生导师,从事智能控制、复杂工业过程建模等研究.
  • 相关文献

参考文献10

  • 1Suichies M, Leroux D, Dechert C, et al. An implementation of generalized predictive control in a flotation plant[J]. Control Engineering Practice, 2000, 8(3): 319 - 325.
  • 2Cilek E C. Application of neural networks to predict locked cycle flotation test results[J]. Minerals Engineering, 2002, 15(12): 1095-1104.
  • 3耿增显,柴天佑.基于案例推理的浮选过程智能优化设定[J].东北大学学报(自然科学版),2008,29(6):761-764. 被引量:18
  • 4Harrave J M, Hall S T. Diagnosis of concentrate grade and mass flowrate in tin flotation from color and surface texture analysis[J]. Mineral Engineering, 1997, 10(6): 6-13.
  • 5Kaartinen J, Hatonen J, Hyotyniemi H, et al. Machinevision-based control of zinc flotation -- A case study[J]. Control Engineering Practice, 2006, 14(12): 1455-1466.
  • 6刘文礼,路迈西,王凡,王勇.煤泥浮选泡沫图像纹理特征的提取及泡沫状态的识别[J].化工学报,2003,54(6):830-835. 被引量:48
  • 7王红平,齐春,李金标,张忠信.基于主成分分析的矿物浮选泡沫图像分类与识别[J].矿冶,2005,14(3):79-82. 被引量:7
  • 8Zhu J, Wang Y K. Application of image recognition system in flotation process[C]. Proc of the 7th WCICA. New York: IEEE Press, 2008: 655-659.
  • 9何学文,赵海鸣.支持向量机及其在机械故障诊断中的应用[J].中南大学学报(自然科学版),2005,36(1):97-101. 被引量:48
  • 10Kennedy J, Eberhart R. Particle swarm optimization[C]. Proc IEEE Int Conf on Neural Networks. Perth: IEEE Press, 1995: 1942-1948.

二级参考文献43

  • 1曾荣,沃国经.图像处理技术在镍选矿厂中的应用[J].矿冶,2002,11(1):37-41. 被引量:11
  • 2刘文礼,路迈西.数字图像处理技术在煤泥浮选泡沫图像纹理特征的提取及识别上的应用[J].选煤技术,2004,32(4):78-81. 被引量:10
  • 3杨辉,王永富,柴天佑.基于案例推理的稀土萃取分离过程优化设定控制[J].东北大学学报(自然科学版),2005,26(3):209-212. 被引量:9
  • 4周晓凯,严普强.用小波分析铁路车辆滚动轴承诊断方法[J].清华大学学报(自然科学版),1996,36(8):29-33. 被引量:17
  • 5吴健康.The Analysis of Digital Image(数字图像分析)[M].Bejing:Peoples Post and Telecommunications Press,1989.245—251.
  • 6刘文礼.The Digital Image Processing for Coal Flotation Froth(煤泥浮选泡沫的数字图像处理):[dissertation](博士后研究报告)[R].Beijing:China University of Mining and Technology(Beijing Campus),2000..
  • 7Moolman D W, Eksteen J J, Aldrich C. The significance of Flotation froth Appearance for Machine Vision Control. Miner.Process, 1996, 48:135-158.
  • 8Woodbum E T, Stockton J B, Robbins D J. Vision - based Charaeterization of Three-phase Froths. In. Proceedings of Intemational Colloquium- Developments in Froth Flotation. South Africa Institute of Mining and Metallurgy, 1989, 1-30.
  • 9Symonds P J, De Jager G. A Technique for Automatically Segmenting Images of the Surface Froth Structures That Are Prevalent in Flotation Cells. In. Proceedings of the 1992 South African Symposium on Communications and Signals processing, Rondebosch, 1992. 111-115.
  • 10Moolman D W, Aldrich C, van Deventer J S J. Digital Image Processing as a Tool for On - line Monitoring of Froth in Flotation Plants. Mineral Engineering, 1994, 7(9): 1149-1164.

共引文献109

同被引文献88

引证文献7

二级引证文献23

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部